Classification of multitemporal remote sensing data using Conditional Random Fields

Hoberg, Thorsten; Rottensteiner, Franz; Heipke, Christian

doi:10.1109/prrs.2010.5742800

Cited by 14 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most widely used classifier is Maximum Likelihood Classifier (MLC), which restrict the data to be assumed to have Gaussian distribution. SVM has a free assumption and ability to find complex classification boundaries with good generalization performance [11]. SVM classifier also has been used to model the unary potential of CRF and exhibited excellent performance [17].In this paper, we adopt SVM classifier to calculate ( | ) i pyx and in this manner SVM is integrated into the unary potential.…”

Section: Unary Potentialmentioning

confidence: 99%

“…A general framework of modelling context information is using Markov random field (MRF) approaches [11][12], which is a classical probabilistic graphical model. However, the interaction between neighbouring image sites (pixels or objects) is restricted to class labels, whereas the features extracted from different image sites are assumed to be conditionally independent [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Object-based Modified Conditional Random Field for Landslide Mapping Using GaoFen-1 Image

Shao¹,

Liu²,

Chen³

et al. 2017

IJSIP

View full text Add to dashboard Cite

show abstract

Section: Unary Potentialmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Object-based Modified Conditional Random Field for Landslide Mapping Using GaoFen-1 Image

Shao¹,

Liu²,

Chen³

et al. 2017

IJSIP

View full text Add to dashboard Cite

show abstract

“…(Roscher et al, 2010) use Import Vector Machines with CRFs to classify regions of Landsat TM images into multiple land cover classes. (Hoberg et al, 2010) adapt CRFs to multi-temporal multi-class land cover classification by adding temporal interactions to the standard unary and spatial potentials. Only few works exist that apply CRFs to semantic segmentation in urban scenes.…”

Section: Related Workmentioning

confidence: 99%

Semantic Segmentation of Aerial Images in Urban Areas With Class-Specific Higher-Order Cliques

Montoya-Zegarra

Wegner

Ladický

et al. 2015

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:In this paper we propose an approach to multi-class semantic segmentation of urban areas in high-resolution aerial images with classspecific object priors for buildings and roads. What makes model design challenging are highly heterogeneous object appearances and shapes that call for priors beyond standard smoothness or co-occurrence assumptions. The data term of our energy function consists of a pixel-wise classifier that learns local co-occurrence patterns in urban environments. To specifically model the structure of roads and buildings, we add high-level shape representations for both classes by sampling large sets of putative object candidates. Buildings are represented by sets of compact polygons, while roads are modeled as a collection of long, narrow segments. To obtain the final pixel-wise labeling, we use a CRF with higher-order potentials that balances the data term with the object candidates. We achieve overall labeling accuracies of > 80%.

show abstract

“…Approaches that take the temporal dependencies into account usually model temporal interaction by class transition matrices that can be determined by an expert (Hoberg et al, 2010) (Hoberg et al, 2011) empirically from existing data sources, * Corresponding author or computed statistically (Leite et al, 2011) (Kenduiywo et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

A Method to Estimate Temporal Interaction in a Conditional Random Field Based Approach for Crop Recognition

Diaz¹,

Feitosa²,

Sanches³

et al. 2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This paper presents a method to estimate the temporal interaction in a Conditional Random Field (CRF) based approach for crop recognition from multitemporal remote sensing image sequences. This approach models the phenology of different crop types as a CRF. Interaction potentials are assumed to depend only on the class labels of an image site at two consecutive epochs. In the proposed method, the estimation of temporal interaction parameters is considered as an optimization problem, whose goal is to find the transition matrix that maximizes the CRF performance, upon a set of labelled data. The objective functions underlying the optimization procedure can be formulated in terms of different accuracy metrics, such as overall and average class accuracy per crop or phenological stages. To validate the proposed approach, experiments were carried out upon a dataset consisting of 12 co-registered LANDSAT images of a region in southeast of Brazil. Pattern Search was used as the optimization algorithm. The experimental results demonstrated that the proposed method was able to substantially outperform estimates related to joint or conditional class transition probabilities, which rely on training samples.

show abstract

Classification of multitemporal remote sensing data using Conditional Random Fields

Cited by 14 publications

References 10 publications

An Object-based Modified Conditional Random Field for Landslide Mapping Using GaoFen-1 Image

An Object-based Modified Conditional Random Field for Landslide Mapping Using GaoFen-1 Image

Semantic Segmentation of Aerial Images in Urban Areas With Class-Specific Higher-Order Cliques

A Method to Estimate Temporal Interaction in a Conditional Random Field Based Approach for Crop Recognition

Contact Info

Product

Resources

About